adaptive-communication
Use when detecting ambiguous user intent, hedging language, open-ended framing, personal context before requests, or when unsure whether user wants exploration vs direct answer. Applies to all conversations.
65
57%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./adaptive-communication/skills/adaptive-communication/SKILL.mdQuality
Discovery
14%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description is heavily skewed toward trigger conditions while completely omitting what the skill actually does. The phrase 'Applies to all conversations' undermines distinctiveness and would cause this skill to compete with every other skill in a multi-skill environment. The trigger terms, while somewhat specific conceptually, describe meta-conversational patterns rather than user-facing language.
Suggestions
Add a clear 'what' clause describing the concrete actions this skill performs (e.g., 'Asks clarifying questions to disambiguate user intent before proceeding' or 'Provides structured exploration of options when user goals are unclear').
Remove or narrow 'Applies to all conversations' to a more specific scope—this phrase guarantees conflict with every other skill and provides no selection signal.
Replace meta-analytical trigger terms like 'hedging language' and 'open-ended framing' with natural user phrases or patterns that Claude can match against (e.g., 'when user says things like "I'm not sure if..." or "maybe I want..." or asks broad questions without clear deliverables').
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description lacks concrete actions. It mentions 'detecting ambiguous user intent' and 'hedging language' but never states what the skill actually does in response. There are no specific capabilities listed—only trigger conditions. | 1 / 3 |
Completeness | The description answers 'when' (detecting ambiguous intent, hedging language, etc.) but completely fails to answer 'what does this do'. There is no indication of what action or output the skill produces. The 'what' is entirely missing. | 1 / 3 |
Trigger Term Quality | It includes some relevant conceptual triggers like 'ambiguous user intent', 'hedging language', 'open-ended framing', and 'exploration vs direct answer', but these are not natural terms users would say. Users don't typically say 'hedging language' or 'ambiguous intent'—these are meta-analytical terms rather than user-facing keywords. | 2 / 3 |
Distinctiveness Conflict Risk | 'Applies to all conversations' is explicitly stated, making this maximally generic. It could trigger for virtually any interaction since ambiguity and open-ended framing are common in most user requests, creating high conflict risk with every other skill. | 1 / 3 |
Total | 5 / 12 Passed |
Implementation
100%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is an excellent skill file that efficiently maps communication signals to concrete response strategies. It's well-structured with tables for quick scanning, provides specific example phrases for both detection and response, and includes important anti-patterns that prevent common mistakes. The quick reference section at the end serves as an effective decision tree.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is lean and well-structured with tables and concise bullet points. It avoids explaining concepts Claude already knows (like what hedging language is in general terms) and instead focuses on actionable signal-to-response mappings. Every section earns its place. | 3 / 3 |
Actionability | Provides concrete detection signals with examples, specific response templates with exact phrasing (e.g., clarification questions), and clear anti-patterns. The guidance is specific enough to act on immediately—exact phrases to use, exact behaviors to avoid. | 3 / 3 |
Workflow Clarity | For this type of skill (conversational adaptation, not a multi-step destructive operation), the workflow is clear: detect signals → classify context type → apply corresponding response adaptation → handle edge cases. The quick reference at the end provides an unambiguous decision tree. No validation/verification gaps since this isn't a destructive or batch operation. | 3 / 3 |
Progressive Disclosure | Content is well-organized into logical sections (detection → response → edge cases → anti-patterns → triggers → quick reference) with appropriate use of tables and lists. At ~80 lines, the content is appropriately sized for a single file with no need for external references, and the structure supports easy scanning. | 3 / 3 |
Total | 12 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- bencium/bencium-marketplace
- Commit
20077d3
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.